Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial behavior beyond that: alias expansion, the three-way verdict taxonomy with best candidate and one-line reason, and the paid x402/USDC-on-Base cost of $0.003. Disclosing the payment rail is exactly the kind of operational prerequisite annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences ordered by importance: what it does, when to use it, what it returns, what it costs. No filler, and the operational cost warning is placed last where it belongs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return contract itself and does so adequately via the three named verdicts plus candidate and reason. Minor gap: no mention of how name variations or partial matches are handled, or whether the $0.003 is charged on errors, but nothing essential to a correct call is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50% — the `type` enum values have no per-field description, but the description's enumeration of 'person, company, vessel or aircraft' maps directly onto that enum and clarifies what the `name` field should contain. That compensates for most of the gap without adding format or normalization rules for names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (screen) and a precisely bounded resource (person, company, vessel or aircraft name) against named datasets (OFAC SDN and Consolidated, including aliases). This is clearly distinguishable from sibling tools like check_wallet_sanctions or sanctions_list_status, which operate on different subjects.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete triggering contexts — before onboarding a customer, paying a supplier, or signing a counterparty — which tells the agent exactly when to reach for it. It stops short of naming alternatives or exclusions (e.g., wallet vs. name screening), so routing to the correct sibling is only partially resolved.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.